سلام
کتابخونه tensorflow ایده کلیش خیلی شبیه به numpy هست و توابع پایهشون تقریبا یه جور عمل می کنن
مثلا برای همین tensordot که گفتید، دقیقا همین تابع توی tensorflow با همین طرز صدا زدن و عملکرد وجود داره و می تونید ازش استفاده کنید
https://www.tensorflow.org/api_docs/python/tf/tensordot
Aliases:
tf.linalg.tensordot
tf.tensordot
tf.tensordot(
a,
b,
axes,
name=None
)
Defined in tensorflow/python/ops/math_ops.py.
See the guide: Math > Tensor Math Function
Tensor contraction of a and b along specified axes.
Tensordot (also known as tensor contraction) sums the product of
elements from a and b over the indices specified by a_axes and b_axes.
The lists a_axes and b_axes specify those pairs of axes along which to
contract the tensors. The axis a_axes[i] of a must have the same
dimension as axis b_axes[i] of b for all i in range(0, len(a_axes)).
The lists a_axes and b_axes must have identical length and consist of
unique integers that specify valid axes for each of the tensors.
This operation corresponds to numpy.tensordot(a, b, axes).
Example 1: When a and b are matrices (order 2), the case axes = 1 is equivalent to matrix multiplication.
Example 2: When a and b are matrices (order 2), the case axes = [[1], [0]] is equivalent to matrix multiplication.
Example 3:
Suppose that and represent two tensors of order 3. Then, contract(a, b, [[0], [2]]) is the order 4 tensor whose entry corresponding to the indices is given by.
In general, order(c) = order(a) + order(b) - 2*len(axes[0]).
Args:
a: Tensor of type float32 or float64.
b: Tensor with the same type as a.
axes: Either a scalar N, or a list or an int32 Tensor of shape [2, k]. If axes is a scalar, sum over the last N axes of a and the first N
axes of b in order. If axes is a list or Tensor the first and second
row contain the set of unique integers specifying axes along which the
contraction is computed, for a and b, respectively. The number of axes
for a and b must be equal.
name: A name for the operation (optional).
Returns:
A Tensor with the same type as a. Raises:
ValueError: If the shapes of a, b, and axes are incompatible.
IndexError: If the values in axes exceed the rank of the corresponding tensor.